US Patent Issued to GOOGLE on Nov. 3 for "Minimum bayes risk decoding with neural quality metrics" (Virginia, California Inventors)

ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,783,872, issued on Nov. 3, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Minimum bayes risk decoding with neural quality metrics" was invented by Qijun Tan (Falls Church, Va.), Markus Freitag (Los Altos, Calif.) and David Grangier (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Provided are systems and methods for sequence-to-sequence modeling with neural quality metrics. More particularly, example aspects of the present disclosure relate to minimum bayes risk (MBR) decoding with neural metrics for machine translation. According to example aspects of the present disclosure, a set of candidate outputs can be sampled from a mac...